FaceTimeMap

International Journal of Multimedia Data Engineering and Management Pub Date : 2019-04-01 DOI:10.4018/ijmdem.2019040103

Buddha Shrestha, Haeyong Chung, R. S. Aygün

{"title":"FaceTimeMap","authors":"Buddha Shrestha, Haeyong Chung, R. S. Aygün","doi":"10.4018/ijmdem.2019040103","DOIUrl":null,"url":null,"abstract":"In this article, the authors study bitmap indexing for temporal querying of faces that appear in videos.Sincethebitmapindexisoriginallydesignedtoselectasetofrecordsthatsatisfyavalue inthedomainoftheattribute,thereisnoclearstrategyforhowtoapplyitfortemporalquerying. Accordingly,theauthorsintroduceamulti-levelbitmapindexthattheauthorscall“FaceTimeMap” for temporal querying of faces in videos. The first level of the FaceTimeMap index is used for determiningwhetherapersonappearsinavideoornot,whereasthesecondleveloftheindexis usedfordeterminingintervalswhenapersonappears.First,theauthorsanalyzetheco-appearance querywheretwoormorepeopleappearsimultaneouslyinavideo,andthenexaminenext-appearance querywhereapersonappearsrightafteranotherperson.Inaddition,toconsiderthegapbetweenthe appearanceofpeople,theauthorsstudyeventual-andprior-appearancequeries.Queriesaresatisfied byapplyingbitwiseoperationsontheFaceTimeMapindex.Theauthorsprovidesomeperformance studiesassociatedwiththisindex. KEywoRDS Allen’s Intervals, Co-Appearance, Eventual-Appearance, Face Search, Next-Appearance","PeriodicalId":445080,"journal":{"name":"International Journal of Multimedia Data Engineering and Management","volume":"95 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Multimedia Data Engineering and Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijmdem.2019040103","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

Abstract

In this article, the authors study bitmap indexing for temporal querying of faces that appear in videos.Sincethebitmapindexisoriginallydesignedtoselectasetofrecordsthatsatisfyavalue inthedomainoftheattribute,thereisnoclearstrategyforhowtoapplyitfortemporalquerying. Accordingly,theauthorsintroduceamulti-levelbitmapindexthattheauthorscall“FaceTimeMap” for temporal querying of faces in videos. The first level of the FaceTimeMap index is used for determiningwhetherapersonappearsinavideoornot,whereasthesecondleveloftheindexis usedfordeterminingintervalswhenapersonappears.First,theauthorsanalyzetheco-appearance querywheretwoormorepeopleappearsimultaneouslyinavideo,andthenexaminenext-appearance querywhereapersonappearsrightafteranotherperson.Inaddition,toconsiderthegapbetweenthe appearanceofpeople,theauthorsstudyeventual-andprior-appearancequeries.Queriesaresatisfied byapplyingbitwiseoperationsontheFaceTimeMapindex.Theauthorsprovidesomeperformance studiesassociatedwiththisindex. KEywoRDS Allen’s Intervals, Co-Appearance, Eventual-Appearance, Face Search, Next-Appearance

查看原文本刊更多论文

在本文中，作者研究了位图索引对视频中出现的人脸进行时态查询。由于位图索引最初设计用于选择满足属性域中某个值的一组记录，因此对于如何将其应用于临时查询没有明确的策略。因此，作者引入了一个多层次的位图索引，作者称之为“FaceTimeMap”，用于视频中人脸的实时查询。FaceTimeMap索引的第一级用于确定一个人是否出现在视频中，而索引的第二级用于确定一个人出现的时间间隔。首先，作者分析了两个或更多的人同时出现在视频中的共同出现查询，然后研究了一个人紧接着出现在另一个人之后的下一个出现查询。此外，为了考虑人们外表之间的差距，作者研究了最终外表和先前外表的查询。查询通过在FaceTimeMap索引上应用按位操作来满足。作者提供了一些与该指数相关的性能研究。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Multimedia Data Engineering and Management

自引率

0.00%

发文量